The DOI matches its Crossref record; 11 of the 13 references it cites were found in a registry or an index, and 2 are not checked yet.
The Memorization Problem: Can We Trust LLMs' Economic Forecasts?
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source doesn’t support the claim as written.
In the citing paper
“This sample period ensures that our evaluation is out-of-sample as the training data of the ChatGPT models stops in September 2021 (e.g., Sarkar and Vafa (2024) and Lopez-Lira, Tang, and Zhu (2025)).”
From Can ChatGPT forecast stock price movements? Return predictability and large language models (2026) · cites this paper as Lopez-Lira, Tang, and Zhu (2025)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredIn the citing paper
“This sample period is selected to avoid look-ahead bias and ensure an out-of-sample evaluation of LLMs like ChatGPT, as the version we evaluate was trained on data up until September 2021.”
From Can ChatGPT forecast stock price movements? Return predictability and large language models (2026) · cites this paper as Lopez-Lira, Tang, and Zhu (2025)
In the citing paper
“recent work by Lopez-Lira, Tang, and Zhu (2025) provides a comprehensive set of evidence that ChatGPT can accurately recall economic and financial information, including macroeconomic variables, stock returns, news headlines, and earnings call content, before the model's knowledge cutoff, and finds no evidence of lookahead bias or memorization after the cutoff”
From Can ChatGPT forecast stock price movements? Return predictability and large language models (2026) · cites this paper as Lopez-Lira, Tang, and Zhu (2025)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Can ChatGPT forecast stock price movements? Return predictability and large language models
Lopez-Lira, A., & Tang, Y. (2026) · Journal of Financial Economics · doi:10.1016/j.jfineco.2026.104335 · Cited by 425
Self-citationText Embeddings Reveal (Almost) As Much As Text
Morris, J. X., Kuleshov, V., Shmatikov, V., & Rush, A. M. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.765 · Cited by 218
Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
Horton, J. J., Filippas, A., & Manning, B. S. (2023) · arXiv · doi:10.48550/arxiv.2301.07543 · Cited by 47
Large Language Models: An Applied Econometric Framework
Ludwig, J., Mullainathan, S., & Rambachan, A. (2026) · Annual Review of Economics · doi:10.1146/annurev-economics-120925-105620 · Cited by 42
Chen, S., Green, T. C., Gulen, H., & Zhou, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4941906 · Cited by 27
Caution Ahead: Numerical Reasoning and Look‐Ahead Bias in AI Models
LEVY, B. (2026) · Journal of Accounting Research · doi:10.1111/1475-679x.70058 · Cited by 20
Can generative AI help identify peer firms?
Cao, Y., Chen, L., Tucker, J. W., & Wan, C. (2025) · Review of Accounting Studies · doi:10.1007/s11142-025-09892-6 · Cited by 19
Large Language Models and Return Prediction in ChinaPreprint
Tan, L., wu, H., & Zhang, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4712248 · Cited by 14
Assessing Look-Ahead Bias in Stock Return Predictions Generated By GPT Sentiment Analysis
Glasserman, P., & Lin, C. (2023) · arXiv · Cited by 12
Generative AI, Managerial Expectations, and Economic Activity
Jha, M., Qian, J., Weber, M., & Yang, B. (2026) · National Bureau of Economic Research · doi:10.48550/arxiv.2410.03897 · Cited by 8
Research works printed but not linked: 16
- John Bai, 2023, Executives vs. chatbots: Unmasking insights through human-AI differences in earnings conference Q&A, Northeastern U. D'Amore-McKim School of Business Research Paper
- Shaun A Bond, 2024, Large language models and financial market sentiment
- Adam Bozman, 2025, Better Than a Coin Flip? Merger Success and Artificial Intelligence Models
- Christian Breitung, 2025, Global Business Networks, Journal of Financial Economics, 166
- J Bybee, 2023, The Ghost in the Machine: Generating Beliefs with Large Language Models
- Chen, 2022, Expected Returns and Large Language Models, Pre-published
- Dominik Degen, 2024, Large Language Models and M&A: Can ChatGPT Help Forecast M&A Activity?, Pre-published
- Joseph Engelberg, 2025, Entity Neutering, Pre-published
- Songrun He, 2025, Chronologically Consistent Large Language Models, Pre-published
- Alex Kim, 2024, Financial statement analysis with large language models
- Benjamin S Manning, 2024, Automated Social Science: Language Models as Scientist and Subjects
- John Morris, 2024, Language Model Inversion, The Twelfth International Conference on Learning Representations
- Eghbal Rahimikia, 2024, Re(Visiting) Large Language Models in Finance, Pre-published
- Jillian Ross, 2024, LLM Economicus? Mapping the Behavioral Biases of LLMs via Utility Theory, Pre-published
- Suproteem Sarkar, 2024, Lookahead Bias in Pretrained Language Models
- Suproteem K Sarkar, 2024, StoriesLM: A Family of Language Models With Time-Indexed Training Data, Pre-published
Cited by
Can ChatGPT forecast stock price movements? Return predictability and large language models
Lopez-Lira, A., & Tang, Y. (2026) · Journal of Financial Economics · doi:10.1016/j.jfineco.2026.104335 · Cited by 425
Self-citationDetecting Lookahead Bias in LLM ForecastsPreprint
Gao, Z., Jiang, W., & Yan, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.23847 · Cited by 27
AI Democratization and Trading Inequality
CHANG, A. Y., DONG, X., Martin, X., & Zhou, C. (2026) · Journal of Accounting Research · doi:10.1111/1475-679x.70063 · Cited by 24
Asirvatham, H., Mokski, E., & Shleifer, A. (2026) · National Bureau of Economic Research · doi:10.3386/w34834 · Cited by 22
Evaluating LLMs in Finance Requires Explicit Bias ConsiderationPreprint
Kong, Y., Lee, H., Hwang, Y., Lopez-Lira, A., Levy, B. (., Mehta, D. B., Wen, Q., Choi, C., Lee, Y., & Zohren, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.14233 · Cited by 20
Self-citation
Metadata
- Authors
- Lopez-Lira, A., Tang, Y., & Zhu, M.
- Affiliations
- University of Florida (US)
- Corresponding author
- Lopez-Lira, Alejandro
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2025
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W4409569681
- Cited by
- 36
- References
- 11
- Citations by year
- 2026: 26 · 2025: 9
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Keywords
- large language models, memorization, economic forecasting, data leakage, stock returns, economic indicators, news headlines, conference calls, motivated reasoning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The Memorization Problem: Can We Trust LLMs' Economic Forecasts? https://app.cochat.ai/papers/10.2139/ssrn.5217505
- The paper
- Lopez-Lira, A., Tang, Y., & Zhu, M. (2025). The Memorization Problem: Can We Trust LLMs' Economic Forecasts? SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5217505
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.